Utility of models to predict 28-day or 30-day unplanned hospital readmissions: an updated systematic review

Using machine learning methods to predict all-cause somatic hospitalizations in adults: A systematic review

AIM

In this review, we investigated how Machine Learning (ML) was utilized to predict all-cause somatic hospital admissions and readmissions in adults.

METHODS

We searched eight databases (PubMed, Embase, Web of Science, CINAHL, ProQuest, OpenGrey, WorldCat, and MedNar) from their inception date to October 2023, and included records that predicted all-cause somatic hospital admissions and readmissions of adults using ML methodology. We used the CHARMS checklist for data extraction, PROBAST for bias and applicability assessment, and TRIPOD for reporting quality.

RESULTS

We screened 7,543 studies of which 163 full-text records were read and 116 met the review inclusion criteria. Among these, 45 predicted admission, 70 predicted readmission, and one study predicted both. There was a substantial variety in the types of datasets, algorithms, features, data preprocessing steps, evaluation, and validation methods. The most used types of features were demographics, diagnoses, vital signs, and laboratory tests. Area Under the ROC curve (AUC) was the most used evaluation metric. Models trained using boosting tree-based algorithms often performed better compared to others. ML algorithms commonly outperformed traditional regression techniques. Sixteen studies used Natural language processing (NLP) of clinical notes for prediction, all studies yielded good results. The overall adherence to reporting quality was poor in the review studies. Only five percent of models were implemented in clinical practice. The most frequently inadequately addressed methodological aspects were: providing model interpretations on the individual patient level, full code availability, performing external validation, calibrating models, and handling class imbalance.

CONCLUSION

This review has identified considerable concerns regarding methodological issues and reporting quality in studies investigating ML to predict hospitalizations. To ensure the acceptability of these models in clinical settings, it is crucial to improve the quality of future studies.

Comparison of machine-learning and logistic regression models for prediction of 30-day unplanned readmission in electronic health records: A development and validation study

It is expected but unknown whether machine-learning models can outperform regression models, such as a logistic regression (LR) model, especially when the number and types of predictor variables increase in electronic health records (EHRs). We aimed to compare the predictive performance of gradient-boosted decision tree (GBDT), random forest (RF), deep neural network (DNN), and LR with the least absolute shrinkage and selection operator (LR-LASSO) for unplanned readmission. We used EHRs of patients discharged alive from 38 hospitals in 2015-2017 for derivation and in 2018 for validation, including basic characteristics, diagnosis, surgery, procedure, and drug codes, and blood-test results. The outcome was 30-day unplanned readmission. We created six patterns of data tables having different numbers of binary variables (that ≥5% or ≥1% of patients or ≥10 patients had) with and without blood-test results. For each pattern of data tables, we used the derivation data to establish the machine-learning and LR models, and used the validation data to evaluate the performance of each model. The incidence of outcome was 6.8% (23,108/339,513 discharges) and 6.4% (7,507/118,074 discharges) in the derivation and validation datasets, respectively. For the first data table with the smallest number of variables (102 variables that ≥5% of patients had, without blood-test results), the c-statistic was highest for GBDT (0.740), followed by RF (0.734), LR-LASSO (0.720), and DNN (0.664). For the last data table with the largest number of variables (1543 variables that ≥10 patients had, including blood-test results), the c-statistic was highest for GBDT (0.764), followed by LR-LASSO (0.755), RF (0.751), and DNN (0.720), suggesting that the difference between GBDT and LR-LASSO was small and their 95% confidence intervals overlapped. In conclusion, GBDT generally outperformed LR-LASSO to predict unplanned readmission, but the difference of c-statistic became smaller as the number of variables was increased and blood-test results were used.

Risk Factors for Unplanned Readmission in Adult Liver Transplant Patients: A Retrospective Study

INTRODUCTION

Unplanned readmission is an important indicator for evaluating medical care quality. Adult liver transplant patients have high risk for readmission, which seriously affects their recovery. As there is currently a lack of research on risk factors for unplanned readmission of adult liver transplant patients in China, the purpose of this study was to elucidate such risk factors.

METHODS

Data for patients undergoing liver transplantation surgery at a tertiary hospital in Zhejiang Province from March 2018 to July 2022 were retrospectively collected. Patients were divided into readmission and nonreadmission groups based on whether unplanned readmission occurred within 90 days. Univariate analysis and logistic regression were used to analyze risk factors for unplanned readmission.

RESULTS

In total, 123 adult liver transplant patients were included; 38 had unplanned readmission, for a rate of 30.8%. There was a statistically significant difference between the groups in terms of age, educational level, operation time, intraoperative bleeding volume, number of complications, postoperative hospital stay, and hemoglobin (P < .05). Logistic regression analysis showed that age [OR = 1.085, 95% CI (1.022, 1.152)], operation time [OR = 1.010, 95% CI (1.001, 1.020)], postoperative hospital stay [OR = 1.124, 95% CI (1.023, 1.235)], and number of complications [OR = 4.487, 95% CI (1.234, 16.319)] were independent risk factors for unplanned readmission in adult liver transplant patients (P < .05).

CONCLUSIONS

The current situation of unplanned readmission for adult liver transplant patients cannot be ignored, indicating that staff should identify risk factors for unplanned readmission as soon as possible and take targeted personalized measures and health education to reduce readmission risk.

Evaluating Algorithmic Bias in 30-Day Hospital Readmission Models: Retrospective Analysis

BACKGROUND

The adoption of predictive algorithms in health care comes with the potential for algorithmic bias, which could exacerbate existing disparities. Fairness metrics have been proposed to measure algorithmic bias, but their application to real-world tasks is limited.

OBJECTIVE

This study aims to evaluate the algorithmic bias associated with the application of common 30-day hospital readmission models and assess the usefulness and interpretability of selected fairness metrics.

METHODS

We used 10.6 million adult inpatient discharges from Maryland and Florida from 2016 to 2019 in this retrospective study. Models predicting 30-day hospital readmissions were evaluated: LACE Index, modified HOSPITAL score, and modified Centers for Medicare & Medicaid Services (CMS) readmission measure, which were applied as-is (using existing coefficients) and retrained (recalibrated with 50% of the data). Predictive performances and bias measures were evaluated for all, between Black and White populations, and between low- and other-income groups. Bias measures included the parity of false negative rate (FNR), false positive rate (FPR), 0-1 loss, and generalized entropy index. Racial bias represented by FNR and FPR differences was stratified to explore shifts in algorithmic bias in different populations.

RESULTS

The retrained CMS model demonstrated the best predictive performance (area under the curve: 0.74 in Maryland and 0.68-0.70 in Florida), and the modified HOSPITAL score demonstrated the best calibration (Brier score: 0.16-0.19 in Maryland and 0.19-0.21 in Florida). Calibration was better in White (compared to Black) populations and other-income (compared to low-income) groups, and the area under the curve was higher or similar in the Black (compared to White) populations. The retrained CMS and modified HOSPITAL score had the lowest racial and income bias in Maryland. In Florida, both of these models overall had the lowest income bias and the modified HOSPITAL score showed the lowest racial bias. In both states, the White and higher-income populations showed a higher FNR, while the Black and low-income populations resulted in a higher FPR and a higher 0-1 loss. When stratified by hospital and population composition, these models demonstrated heterogeneous algorithmic bias in different contexts and populations.

CONCLUSIONS

Caution must be taken when interpreting fairness measures' face value. A higher FNR or FPR could potentially reflect missed opportunities or wasted resources, but these measures could also reflect health care use patterns and gaps in care. Simply relying on the statistical notions of bias could obscure or underplay the causes of health disparity. The imperfect health data, analytic frameworks, and the underlying health systems must be carefully considered. Fairness measures can serve as a useful routine assessment to detect disparate model performances but are insufficient to inform mechanisms or policy changes. However, such an assessment is an important first step toward data-driven improvement to address existing health disparities.

Improvement of scoring system used before discharge to predict 30-day all-cause unplanned readmission in geriatric population: a prospective cohort study

BACKGROUND

Data taken from tertiary referral hospitals in Indonesia suggested readmission rate in older population ranging between 18.1 and 36.3%. Thus, it is crucial to identify high risk patients who were readmitted. Our previous study found several important predictors, despite unsatisfactory discrimination value.

METHODS

We aimed to investigate whether comprehensive geriatric assessment (CGA) -based modification to the published seven-point scoring system may increase the discrimination value. We conducted a prospective cohort study in July-September 2022 and recruited patients aged 60 years and older admitted to the non-surgical ward and intensive coronary care unit. The ROC curve was made based on the four variables included in the prior study. We conducted bivariate and multivariate analyses, and derived a new scoring system with its discrimination value.

RESULTS

Of 235 subjects, the incidence of readmission was 32.3% (95% CI 26-38%). We established a new scoring system consisting of 4 components. The scoring system had maximum score of 21 and incorporated malignancy (6 points), delirium (4 points), length of stay ≥ 10 days (4 points), and being at risk of malnutrition or malnourished (7 points), with a good calibration test. The C-statistic value was 0.835 (95% CI 0.781-0.880). The optimal cut-off point was ≥ 8 with a sensitivity of 90.8% and a specificity of 54.7%.

CONCLUSIONS

Malignancy, delirium, length of stay ≥ 10 days, and being at risk of malnutrition or malnourished are predictors for 30-day all-cause unplanned readmission. The sensitive scoring system is a strong model to identify whether an individual is at higher risk for readmission. The new CGA-based scoring system had higher discrimination value than that of the previous seven-point scoring system.

Machine Learning Model for Readmission Prediction of Patients With Heart Failure Based on Electronic Health Records: Protocol for a Quasi-Experimental Study for Impact Assessment

BACKGROUND

Care for patients with heart failure (HF) causes a substantial load on health care systems where a prominent challenge is the elevated rate of readmissions within 30 days following initial discharge. Clinical professionals face high levels of uncertainty and subjectivity in the decision-making process on the optimal timing of discharge. Unwanted hospital stays generate costs and cause stress to patients and potentially have an impact on care outcomes. Recent studies have aimed to mitigate the uncertainty by developing and testing risk assessment tools and predictive models to identify patients at risk of readmission, often using novel methods such as machine learning (ML).

OBJECTIVE

This study aims to investigate how a developed clinical decision support (CDS) tool alters the decision-making processes of health care professionals in the specific context of discharging patients with HF, and if so, in which ways. Additionally, the aim is to capture the experiences of health care practitioners as they engage with the system's outputs to analyze usability aspects and obtain insights related to future implementation.

METHODS

A quasi-experimental design with randomized crossover assessment will be conducted with health care professionals on HF patients' scenarios in a region located in the South of Sweden. In total, 12 physicians and nurses will be randomized into control and test groups. The groups shall be provided with 20 scenarios of purposefully sampled patients. The clinicians will be asked to take decisions on the next action regarding a patient. The test group will be provided with the 10 scenarios containing patient data from electronic health records and an outcome from an ML-based CDS model on the risk level for readmission of the same patients. The control group will have 10 other scenarios without the CDS model output and containing only the patients' data from electronic medical records. The groups will switch roles for the next 10 scenarios. This study will collect data through interviews and observations. The key outcome measures are decision consistency, decision quality, work efficiency, perceived benefits of using the CDS model, reliability, validity, and confidence in the CDS model outcome, integrability in the routine workflow, ease of use, and intention to use. This study will be carried out in collaboration with Cambio Healthcare Systems.

RESULTS

The project is part of the Center for Applied Intelligent Systems Research Health research profile, funded by the Knowledge Foundation (2021-2028). Ethical approval for this study was granted by the Swedish ethical review authority (2022-07287-02). The recruitment process of the clinicians and the patient scenario selection will start in September 2023 and last till March 2024.

CONCLUSIONS

This study protocol will contribute to the development of future formative evaluation studies to test ML models with clinical professionals.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/52744.

Hospital Readmissions for Fluid Overload among Individuals with Diabetes and Diabetic Kidney Disease: Risk Factors and Multivariable Prediction Models

AIMS

Hospital readmissions due to recurrent fluid overload in diabetes and diabetic kidney disease can be avoided with evidence-based interventions. We aimed to identify at-risk patients who can benefit from these interventions by developing risk prediction models for readmissions for fluid overload in people living with diabetes and diabetic kidney disease.

METHODS

This was a single-center retrospective cohort study of 1,531 adults with diabetes and diabetic kidney disease hospitalized for fluid overload, congestive heart failure, pulmonary edema, and generalized edema between 2015 and 2017. The multivariable regression models for 30-day and 90-day readmission for fluid overload were compared with the LACE score for discrimination, calibration, sensitivity, specificity, and net reclassification index (NRI).

RESULTS

Readmissions for fluid overload within 30 days and 90 days occurred in 8.6% and 17.2% of patients with diabetes, and 8.2% and 18.3% of patients with diabetic kidney disease, respectively. After adjusting for demographics, comorbidities, clinical parameters, and medications, a history of alcoholism (HR 3.85, 95% CI: 1.41-10.55) and prior hospitalization for fluid overload (HR 2.50, 95% CI: 1.26-4.96) were independently associated with 30-day readmission in patients with diabetic kidney disease, as well as in individuals with diabetes. Additionally, current smoking, absence of hypertension, and high-dose intravenous furosemide were also associated with 30-day readmission in individuals with diabetes. Prior hospitalization for fluid overload (HR 2.43, 95% CI: 1.50-3.94), cardiovascular disease (HR 1.44, 95% CI: 1.03-2.02), eGFR ≤45 mL/min/1.73 m2 (HR 1.39, 95% CI: 1.003-1.93) was independently associated with 90-day readmissions in individuals with diabetic kidney disease. Additionally, thiazide prescription at discharge reduced 90-day readmission in diabetic kidney disease, while the need for high-dose intravenous furosemide predicted 90-day readmission in diabetes. The clinical and clinico-psychological models for 90-day readmission in individuals with diabetes and diabetic kidney disease had better discrimination and calibration than the LACE score. The NRI for the clinico-psychosocial models to predict 30- and 90-day readmissions in diabetes was 22.4% and 28.9%, respectively. The NRI for the clinico-psychosocial models to predict 30- and 90-day readmissions in diabetic kidney disease was 5.6% and 38.9%, respectively.

CONCLUSION

The risk models can potentially be used to identify patients at risk of readmission for fluid overload for evidence-based interventions, such as patient education or transitional care programs to reduce preventable hospitalizations.

An overview of reviews and synthesis across 440 studies examines the importance of hospital readmission predictors across various patient populations

OBJECTIVES

The scientific literature contains an abundance of prediction models for hospital readmissions. However, no review has yet synthesized their predictors across various patient populations. Therefore, our aim was to examine predictors of hospital readmissions across 13 patient populations.

STUDY DESIGN AND SETTING

An overview of systematic reviews was combined with a meta-analytical approach. Two thousand five hundred four different predictors were categorized using common ontologies to pool and examine their odds ratios and frequencies of use in prediction models across and within different patient populations.

RESULTS

Twenty-eight systematic reviews with 440 primary studies were included. Numerous predictors related to prior use of healthcare services (odds ratio; 95% confidence interval: 1.64; 1.42-1.89), diagnoses (1.41; 1.31-1.51), health status (1.35; 1.20-1.52), medications (1.28; 1.13-1.44), administrative information about the index hospitalization (1.23; 1.14-1.33), clinical procedures (1.20; 1.07-1.35), laboratory results (1.18; 1.11-1.25), demographic information (1.10; 1.06-1.14), and socioeconomic status (1.07; 1.02-1.11) were analyzed. Diagnoses were frequently used (in 37.38%) and displayed large effect sizes across all populations. Prior use of healthcare services showed the largest effect sizes but were seldomly used (in 2.57%), whereas demographic information (in 13.18%) was frequently used but displayed small effect sizes.

CONCLUSION

Diagnoses and patients' prior use of healthcare services showed large effects both across and within different populations. These results can serve as a foundation for future prediction modeling.

Early repeat hospitalization for fluid overload in individuals with cardiovascular disease and risks: a retrospective cohort study

AIMS

Fluid overload is a common manifestation of cardiovascular and kidney disease and a leading cause of hospitalizations. To identify patients at risk of recurrent severe fluid overload, we evaluated the incidence and risk factors associated with early repeat hospitalization for fluid overload among individuals with cardiovascular disease and risks.

METHODS

Single-center retrospective cohort study of 3423 consecutive adults with an index hospitalization for fluid overload between January 2015 and December 2017 and had cardiovascular risks (older age, diabetes mellitus, hypertension, dyslipidemia, kidney disease, known cardiovascular disease), but excluded if lost to follow-up or eGFR < 15 ml/min/1.73 m2. The outcome was early repeat hospitalization for fluid overload within 30 days of discharge.

RESULTS

The mean age was 73.9 ± 11.6 years and eGFR was 54.1 ± 24.6 ml/min/1.73 m2 at index hospitalization. Early repeat hospitalization for fluid overload occurred in 291 patients (8.5%). After adjusting for demographics, comorbidities, clinical parameters during index hospitalization and medications at discharge, cardiovascular disease (adjusted odds ratio, OR 1.66, 95% CI 1.27-2.17), prior hospitalization for fluid overload within 3 months (OR 2.52, 95% CI 1.17-5.44), prior hospitalization for any cause in within 6 months (OR 1.33, 95% CI 1.02-1.73) and intravenous furosemide use (OR 1.58, 95% CI 1.10-2.28) were associated with early repeat hospitalization for fluid overload. Higher systolic BP on admission (OR 0.992, 95% 0.986-0.998) and diuretic at discharge (OR 0.50, 95% CI 0.26-0.98) reduced early hospitalization for fluid overload.

CONCLUSION

Patients at-risk of early repeat hospitalization for fluid overload may be identified using these risk factors for targeted interventions.

Patients with repeated acute admissions to somatic departments: sociodemographic characteristics, disease burden, and contact with primary healthcare sector - a retrospective register-based case-control study

BACKGROUND

Healthcare systems face escalating capacity challenges and patients with repeated acute admissions strain hospital resources disproportionately. However, studies investigating the characteristics of such patients across all public healthcare providers in a universal healthcare system are lacking.

OBJECTIVE

To investigate characteristics of patients with repeated acute admissions (three or more acute admissions within a calendar year) in regard to sociodemographic characteristics, disease burden, and contact with the primary healthcare sector.

METHODS

This matched register-based case-control study investigated repeated acute admissions from 1 January 2014 to 31 December 2018, among individuals, who resided in four Danish municipalities. The study included 6169 individuals with repeated acute admissions, matched 1:4 to individuals with no acute admissions and one to two acute admissions, respectively. Group comparisons were conducted using conditional logistic regression.

RESULTS

Receiving social benefits increased the odds of repeated acute admissions 9.5-fold compared with no acute admissions (odds ratio (OR) 9.5; 95% confidence interval (CI) 8.5; 10.6) and 3.4-fold compared with one to two acute admissions (OR 3.4; 95% CI 3.1; 3.7). The odds of repeated acute admissions increased with the number of used medications and chronic diseases. Having a mental illness increased the odds of repeated acute admissions 5.8-fold when compared with no acute admissions (OR 5.7; 95% CI 5.2; 6.4) and 2.3-fold compared with one to two acute admissions (OR 2.3; 95% CI 2.1; 2.5). Also, high use of primary sector services (e.g. nursing care) increased the odds of repeated acute admissions when compared with no acute admissions and one to two acute admissions.

CONCLUSIONS

This study pinpointed key factors encompassing social status, disease burden, and healthcare utilisation as pivotal markers of risk for repeated acute admissions, thus identifying high-risk patients and facilitating targeted intervention.

A machine learning model to predict heart failure readmission: toward optimal feature set

Background

Hospital readmissions for heart failure patients remain high despite efforts to reduce them. Predictive modeling using big data provides opportunities to identify high-risk patients and inform care management. However, large datasets can constrain performance.

Objective

This study aimed to develop a machine learning based prediction model leveraging a nationwide hospitalization database to predict 30-day heart failure readmissions. Another objective of this study is to find the optimal feature set that leads to the highest AUC value in the prediction model.

Material and methods

Heart failure patient data was extracted from the 2020 Nationwide Readmissions Database. A heuristic feature selection process incrementally incorporated predictors into logistic regression and random forest models, which yields a maximum increase in the AUC metric. Discrimination was evaluated through accuracy, sensitivity, specificity and AUC.

Results

A total of 566,019 discharges with heart failure diagnosis were recognized. Readmission rate was 8.9% for same-cause and 20.6% for all-cause diagnoses. Random forest outperformed logistic regression, achieving AUCs of 0.607 and 0.576 for same-cause and all-cause readmissions respectively. Heuristic feature selection resulted in the identification of optimal feature sets including 20 and 22 variables from a pool of 30 and 31 features for the same-cause and all-cause datasets. Key predictors included age, payment method, chronic kidney disease, disposition status, number of ICD-10-CM diagnoses, and post-care encounters.

Conclusion

The proposed model attained discrimination comparable to prior analyses that used smaller datasets. However, reducing the sample enhanced performance, indicating big data complexity. Improved techniques like heuristic feature selection enabled effective leveraging of the nationwide data. This study provides meaningful insights into predictive modeling methodologies and influential features for forecasting heart failure readmissions.

A study protocol for a predictive model to assess population-based avoidable hospitalization risk: Avoidable Hospitalization Population Risk Prediction Tool (AvHPoRT)

INTRODUCTION

Avoidable hospitalizations are considered preventable given effective and timely primary care management and are an important indicator of health system performance. The ability to predict avoidable hospitalizations at the population level represents a significant advantage for health system decision-makers that could facilitate proactive intervention for ambulatory care-sensitive conditions (ACSCs). The aim of this study is to develop and validate the Avoidable Hospitalization Population Risk Tool (AvHPoRT) that will predict the 5-year risk of first avoidable hospitalization for seven ACSCs using self-reported, routinely collected population health survey data.

METHODS AND ANALYSIS

The derivation cohort will consist of respondents to the first 3 cycles (2000/01, 2003/04, 2005/06) of the Canadian Community Health Survey (CCHS) who are 18-74 years of age at survey administration and a hold-out data set will be used for external validation. Outcome information on avoidable hospitalizations for 5 years following the CCHS interview will be assessed through data linkage to the Discharge Abstract Database (1999/2000-2017/2018) for an estimated sample size of 394,600. Candidate predictor variables will include demographic characteristics, socioeconomic status, self-perceived health measures, health behaviors, chronic conditions, and area-based measures. Sex-specific algorithms will be developed using Weibull accelerated failure time survival models. The model will be validated both using split set cross-validation and external temporal validation split using cycles 2000-2006 compared to 2007-2012. We will assess measures of overall predictive performance (Nagelkerke R2), calibration (calibration plots), and discrimination (Harrell's concordance statistic). Development of the model will be informed by the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) statement.

ETHICS AND DISSEMINATION

This study was approved by the University of Toronto Research Ethics Board. The predictive algorithm and findings from this work will be disseminated at scientific meetings and in peer-reviewed publications.

The hospital frailty risk score as a predictor of readmission after ERCP

BACKGROUND AND AIMS

The 30-day readmission rate is a nationally recognized quality measure with nearly one-fifth of patients being readmitted. This study aims to evaluate frailty, as measured by the hospital frailty risk score (HFRS), as a prognostic indicator for 30-day readmission after inpatient ERCP.

METHODS

We analyzed weighted discharge records from the 2017 Nationwide Readmissions Database (NRD) to identify patients undergoing ERCP between 01/01/2017 and 11/30/2017. Our primary outcome was the 30-day unplanned readmission rate in frail (defined as HFRS > 5) against non-frail (HFRS < 5) patients. A mixed effects multivariable logistic regression method was employed.

RESULTS

Among 68,206 weighted hospitalized patients undergoing ERCP, 31.3% were frail. Frailty was associated with higher 30-day readmission (OR 1.23, 95% CI [1.16-1.30]). Multivariable analysis showed a greater risk of readmission with cirrhosis (OR 1.26, 95% CI [1.10-1.45]), liver transplantation (OR 1.36, 95% CI [1.08-1.71]), cancer (OR 1.58, 95% CI [1.48-1.69]), and male gender (OR 1.24, 95% CI [1.18-1.31]). Frail patients also had higher mortality rate (1.8% vs 0.6%, p < 0.01)], longer LOS during readmission (6.7 vs 5.6 days, p < 0.01), and incurred more charges from both hospitalizations ($175,620 vs $132,519, p < 0.01). Sepsis was the most common primary indication for both frail and non-frail readmissions but accounted for a greater percentage of frail readmissions (17.9% vs 12.4%, p < 0.01).

CONCLUSIONS

Frailty is associated with higher readmission rates, mortality, LOS, and hospital charges for admitted patients undergoing ERCP. Sepsis is the leading cause for readmission. Independent risk factors for readmission include liver transplantation, cancer, cirrhosis, and male gender.

Prediction of patient admission and readmission in adults from a Colombian cohort with bipolar disorder using artificial intelligence

Introduction

Bipolar disorder (BD) is a chronically progressive mental condition, associated with a reduced quality of life and greater disability. Patient admissions are preventable events with a considerable impact on global functioning and social adjustment. While machine learning (ML) approaches have proven prediction ability in other diseases, little is known about their utility to predict patient admissions in this pathology.

Aim

To develop prediction models for hospital admission/readmission within 5 years of diagnosis in patients with BD using ML techniques.

Methods

The study utilized data from patients diagnosed with BD in a major healthcare organization in Colombia. Candidate predictors were selected from Electronic Health Records (EHRs) and included sociodemographic and clinical variables. ML algorithms, including Decision Trees, Random Forests, Logistic Regressions, and Support Vector Machines, were used to predict patient admission or readmission. Survival models, including a penalized Cox Model and Random Survival Forest, were used to predict time to admission and first readmission. Model performance was evaluated using accuracy, precision, recall, F1 score, area under the receiver operating characteristic curve (AUC) and concordance index.

Results

The admission dataset included 2,726 BD patients, with 354 admissions, while the readmission dataset included 352 patients, with almost half being readmitted. The best-performing model for predicting admission was the Random Forest, with an accuracy score of 0.951 and an AUC of 0.98. The variables with the greatest predictive power in the Recursive Feature Elimination (RFE) importance analysis were the number of psychiatric emergency visits, the number of outpatient follow-up appointments and age. Survival models showed similar results, with the Random Survival Forest performing best, achieving an AUC of 0.95. However, the prediction models for patient readmission had poorer performance, with the Random Forest model being again the best performer but with an AUC below 0.70.

Conclusion

ML models, particularly the Random Forest model, outperformed traditional statistical techniques for admission prediction. However, readmission prediction models had poorer performance. This study demonstrates the potential of ML techniques in improving prediction accuracy for BD patient admissions.

Predicting 30-day risk from benzodiazepine/Z-drug dispensations in older adults using administrative data: A prognostic machine learning approach

OBJECTIVE

To develop a machine-learning (ML) model using administrative data to estimate risk of adverse outcomes within 30-days of a benzodiazepine (BZRA) dispensation in older adults for use by health departments/regulators.

DESIGN, SETTING AND PARTICIPANTS

This study was conducted in Alberta, Canada during 2018-2019 in Albertans 65 years of age and older. Those with any history of malignancy or palliative care were excluded.

EXPOSURE

Each BZRA dispensation from a community pharmacy served as the unit of analysis.

MAIN OUTCOMES AND MEASURES

ML algorithms were developed on 2018 administrative data to predict risk of any-cause hospitalization, emergency department visit or death within 30-days of a BZRA dispensation. Validation on 2019 administrative data was done using XGBoost to evaluate discrimination, calibration and other relevant metrics on ranked predictions. Daily and quarterly predictions were simulated on 2019 data.

RESULTS

65,063 study participants were included which represented 633,333 BZRA dispensation during 2018-2019. The validation set had 314,615 dispensations linked to 55,928 all-cause outcomes representing a pre-test probability of 17.8%. C-statistic for the XGBoost model was 0.75. Measuring risk at the end of 2019, the top 0.1 percentile of predicted risk had a LR + of 40.31 translating to a post-test probability of 90%. Daily and quarterly classification simulations resulted in uninformative predictions with positive likelihood ratios less than 10 in all risk prediction categories. Previous history of admissions was ranked highest in variable importance.

CONCLUSION

Developing ML models using only administrative health data may not provide health regulators with sufficient informative predictions to use as decision aids for potential interventions, especially if considering daily or quarterly classifications of BZRA risks in older adults. ML models may be informative for this context if yearly classifications are preferred. Health regulators should have access to other types of data to improve ML prediction.

Evaluation of a modified emergency surgical acuity score in predicting operative and non-operative mortality and morbidity in an acute surgical unit

BACKGROUND

Emergency general surgery (EGS) patients have an increased risk of mortality and morbidity compared to other surgical patients. Limited risk assessment tools exist for use in both operative and non-operative EGS patients. We assessed the accuracy of a modified Emergency Surgical Acuity Score (mESAS) in EGS patients at our institution.

METHODS

A retrospective cohort study from an acute surgical unit at a tertiary referral hospital was performed. Primary endpoints assessed included death before discharge, length of stay (LOS) >5 days and unplanned readmission within 28 days. Operative and non-operative patients were analysed separately. Validation was performed using the area under the receiver operating characteristic (AUROC), Brier score and Hosmer-Lemeshow test.

RESULTS

A total of 1763 admissions between March 2018 and June 2021 were included for analysis. The mESAS was an accurate predictor of both death before discharge (AUROC 0.979, Brier score 0.007, Hosmer-Lemeshow P = 0.981) and LOS >5 days (0.787, 0.104, and 0.253, respectively). The mESAS was less accurate in predicting readmission within 28 days (0.639, 0.040, and 0.887, respectively). The mESAS retained its predictive ability for death before discharge and LOS >5 days in the split cohort analysis.

CONCLUSION

This study is the first to validate a modified ESAS in a non-operatively managed EGS population internationally and the first to validate the mESAS in Australia. The mESAS accurately predicts death before discharge and prolonged LOS for all EGS patients, providing a highly useful tool for surgeons and EGS units worldwide.

Community Paramedicine Intervention Reduces Hospital Readmission and Emergency Department Utilization for Patients with Cardiopulmonary Conditions

OBJECTIVE

Patients discharged from the hospital with diagnoses of myocardial infarction, congestive heart failure or acute exacerbation of chronic obstructive pulmonary disease (COPD) have high rates of readmission. We sought to quantify the impact of a community paramedicine (CP) intervention on hospital readmission and emergency department (ED) and clinic utilization for patients discharged with these conditions and to calculate the difference in healthcare costs.

METHODS

This was a prospective, observational cohort study with a matched historical control. The groups were matched for qualifying diagnosis, age, gender, and ZIP code. The intervention group received 1-2 home visits per week by a community paramedic for 30 days. We calculated the number of all-cause hospital readmissions and ED and clinic visits, and used descriptive statistics to compare cohorts.

RESULTS

Included in the study were 78 intervention patients and 78 controls. Compared to controls, fewer subjects in the CP cohort had experienced a readmission at 120 days (34.6% vs 64.1%, P < 0.001) and 210 days (43.6% vs 75.6%, P < 0.001) after discharge. At 210 days the CP cohort had 40.9% fewer total hospital admissions, saving 218 bed days and $410,428 in healthcare costs. The CP cohort had 40.7% fewer total ED visits.

CONCLUSION

Patients who received a post-hospital community paramedic intervention had fewer hospital readmissions and ED visits, which resulted in saving 218 bed days and decreasing healthcare costs by $410,428. Incorporation of a home CP intervention of 30 days in this patient population has the potential to benefit payors, hospitals, and patients.

Independent Predictors of 30-Day Readmission to Acute Psychiatric Wards in Patients With Mental Disorders: A Systematic Review and Meta-Analysis

Psychiatric readmissions have long been considered significant indicators for healthcare planning. The aim of this study was to identify factors influencing early (30-day) readmissions to acute psychiatric wards. A meta-analysis and systematic review were conducted according to Meta-analysis of Observational Studies in Epidemiology (MOOSE) guidelines. Comprehensive database searching was conducted using online databases, including PubMed and Google Scholar, to search for articles identifying factors associated with early (30-day) readmissions to acute psychiatric wards. Keywords used to search for relevant articles included "Mental illness," "readmission," and factors along with their synonyms and Medical Subject Headings (MeSH) terms. The search included studies published between 2011 and June 2023. A total of 13 studies were included in this meta-analysis. The pooled rate of the 30-day readmission was 16% (95% confidence interval: 13%-20%). A pooled analysis showed that factors significantly associated with an unplanned hospital readmission included gender, length of stay, and insurance status as predictors of the unplanned hospital readmission among individuals with psychiatric illness. Additionally, we also found that the rate of 30-day unplanned admissions was greater in patients with schizophrenia, followed by personality disorder, bipolar disorder, depression, and substance use. This study highlights the importance of providing targeted interventions and support for individuals with these conditions to reduce the risk of readmissions.

Evaluating machine learning algorithms to Predict 30-day Unplanned REadmission (PURE) in Urology patients

BACKGROUND

Unplanned hospital readmissions are serious medical adverse events, stressful to patients, and expensive for hospitals. This study aims to develop a probability calculator to predict unplanned readmissions (PURE) within 30-days after discharge from the department of Urology, and evaluate the respective diagnostic performance characteristics of the PURE probability calculator developed with machine learning (ML) algorithms comparing regression versus classification algorithms.

METHODS

Eight ML models (i.e. logistic regression, LASSO regression, RIDGE regression, decision tree, bagged trees, boosted trees, XGBoost trees, RandomForest) were trained on 5.323 unique patients with 52 different features, and evaluated on diagnostic performance of PURE within 30 days of discharge from the department of Urology.

RESULTS

Our main findings were that performances from classification to regression algorithms had good AUC scores (0.62-0.82), and classification algorithms showed a stronger overall performance as compared to models trained with regression algorithms. Tuning the best model, XGBoost, resulted in an accuracy of 0.83, sensitivity of 0.86, specificity of 0.57, AUC of 0.81, PPV of 0.95, and a NPV of 0.31.

CONCLUSIONS

Classification models showed stronger performance than regression models with reliable prediction for patients with high probability of readmission, and should be considered as first choice. The tuned XGBoost model shows performance that indicates safe clinical appliance for discharge management in order to prevent an unplanned readmission at the department of Urology.

Predicting Colorectal Surgery Readmission Risk: a Surgery-Specific Predictive Model

Most current predictive models for risk of readmission were primarily designed from non-surgical patients and often utilize administrative data alone. Models built upon comprehensive data sources specific to colorectal surgery may be key to implementing interventions aimed at reducing readmissions. This study aimed to develop a predictive model for risk of 30-day readmission specific to colorectal surgery patients including administrative, clinical, laboratory, and socioeconomic status (SES) data. Patients admitted to the colorectal surgery service who underwent surgery and were discharged from an academic tertiary hospital between 2017 and 2019 were included. A total of 1549 patients met eligibility criteria for this retrospective split-sample cohort study. The 30-day readmission rate of the cohort was 19.62%. A multivariable logistic regression was developed (C=0.70, 95% CI 0.61-0.73), which outperformed two internationally used readmission risk prediction indices (C=0.58, 95% CI 0.52-0.65) and (C=0.60, 95% CI 0.53-0.66). Tailored surgery-specific readmission models with comprehensive data sources outperform the most used readmission indices in predicting 30-day readmission in colorectal surgery patients. Model performance is improved by using more comprehensive datasets that include administrative and socioeconomic details about a patient, as well as clinical information used for decision-making around the time of discharge.

Predicting Hospital Readmissions in a Commercially Insured Population over Varying Time Horizons

BACKGROUND

Reducing hospital readmissions is a federal policy priority, and predictive models of hospital readmissions have proliferated in recent years; however, most such models tend to focus on the 30-day readmission time horizon and do not consider readmission over shorter (or longer) windows.

OBJECTIVES

To evaluate the performance of a predictive model of hospital readmissions over three different readmission timeframes in a commercially insured population.

DESIGN

Retrospective multivariate logistic regression with an 80/20 train/test split.

PARTICIPANTS

A total of 2,213,832 commercially insured inpatient admissions from 2016 to 2017 comprising 782,768 unique patients from the Health Care Cost Institute.

MAIN MEASURES

Outcomes are readmission within 14 days, 15-30 days, and 31-60 days from discharge. Predictor variables span six different domains: index admission, condition history, demographic, utilization history, pharmacy, and environmental controls.

KEY RESULTS

Our model generates C-statistics for holdout samples ranging from 0.618 to 0.915. The model's discriminative power declines with readmission time horizon: discrimination for readmission predictions within 14 days following discharge is higher than for readmissions 15-30 days following discharge, which in turn is higher than predictions 31-60 days following discharge. Additionally, the model's predictive power increases nonlinearly with the inclusion of successive risk factor domains: patient-level measures of utilization and condition history add substantially to the discriminative power of the model, while demographic information, pharmacy utilization, and environmental risk factors add relatively little.

CONCLUSION

It is more difficult to predict distant readmissions than proximal readmissions, and the more information the model uses, the better the predictions. Inclusion of utilization-based risk factors add substantially to the discriminative ability of the model, much more than any other included risk factor domain. Our best-performing models perform well relative to other published readmission prediction models. It is possible that these predictions could have operational utility in targeting readmission prevention interventions among high-risk individuals.

Identifying Barriers to Post-Acute Care Referral and Characterizing Negative Patient Preferences Among Hospitalized Older Adults Using Natural Language Processing

Our objective was to detect common barriers to post-acute care (B2PAC) among hospitalized older adults using natural language processing (NLP) of clinical notes from patients discharged home when a clinical decision support system recommended post-acute care. We annotated B2PAC sentences from discharge planning notes and developed an NLP classifier to identify the highest-value B2PAC class (negative patient preferences). Thirteen machine learning models were compared with Amazon's AutoGluon deep learning model. The study included 594 acute care notes from 100 patient encounters (1156 sentences contained 11 B2PAC) in a large academic health system. The most frequent and modifiable B2PAC class was negative patient preferences (18.3%). The best supervised model was Extreme Gradient Boosting (F1: 0.859), but the deep learning model performed better (F1: 0.916). Alerting clinicians of negative patient preferences early in the hospitalization can prompt interventions such as patient education to ensure patients receive the right level of care and avoid negative outcomes.

Modelling 30-day hospital readmission after discharge for COPD patients based on electronic health records

Chronic Obstructive Pulmonary Disease (COPD) is the third most common chronic disease in China with frequent exacerbations, resulting in increased hospitalization and readmission rate. COPD readmission within 30 days after discharge is an important indicator of care transitions, patient's quality of life and disease management. Identifying risk factors and improving 30-day readmission prediction help inform appropriate interventions, reducing readmissions and financial burden. This study aimed to develop a 30-day readmission prediction model using decision tree by learning from the data extracted from the electronic health record of COPD patients in Macao. Health records data of COPD inpatients from Kiang Wu Hospital, Macao, from January 1, 2018, to December 31, 2019 were reviewed and analyzed. A total of 782 hospitalizations for AECOPD were enrolled, where the 30-day readmission rate was 26.5% (207). A balanced dataset was randomly generated, where male accounted for 69.1% and mean age was 80.73 years old. Age, length of stay, history of tobacco smoking, hemoglobin, systemic steroids use, antibiotics use and number of hospital admission due to COPD in last 12 months were found to be significant risk factors for 30-day readmission of CODP patients (P < 0.01). A data-driven decision tree-based modelling approach with Bayesian hyperparameter optimization was developed. The mean precision-recall and AUC value for the classifier were 73.85, 73.7 and 0.7506, showing a satisfying prediction performance. The number of hospital admission due to AECOPD in last 12 months, smoke status and patients' age were the top factors for 30-day readmission in Macao population.

Risk factors associated with 30-day unplanned hospital readmission for patients with mental illness

Unplanned hospital readmission rate is up to 43% in mental health settings, which is higher than in general health settings. Unplanned readmissions delay the recovery of patients with mental illness and add financial burden on families and healthcare services. There have been efforts to reduce readmissions with a particular interest in identifying patients at higher readmission risk after index admission; however, the results have been inconsistent. This systematic review synthesized risk factors associated with 30-day unplanned hospital readmissions for patients with mental illness. Eleven electronic databases were searched from 2010 to 30 September 2021 using key terms of 'mental illness', 'readmission' and 'risk factors'. Sixteen studies met the selection criteria for this review. Data were synthesized using content analysis and presented in narrative and tabular form because the extracted risk factors could not be pooled statistically due to methodological heterogeneity of the included studies. Consistently cited readmission predictors were patients with lower educational background, unemployment, previous mental illness hospital admission and more than 7 days of the index hospitalization. Results revealed the complexity of identifying unplanned hospital readmission predictors for people with mental illness. Policymakers need to specify the expected standards that written discharge summary must reach general practitioners concurrently at discharge. Hospital clinicians should ensure that discharge summary summaries are distributed to general practitioners for effective ongoing patient care and management. Having an advanced mental health nurse for patients during their transition period needs to be explored to understand how this role could ensure referrals to the general practitioner are eventuated.

Risk factors associated with 31-day unplanned hospital readmission in newborns: a systematic review

The purpose of this study is to synthesize evidence on risk factors associated with newborn 31-day unplanned hospital readmissions (UHRs). A systematic review was conducted searching CINAHL, EMBASE (Ovid), and MEDLINE from January 1st 2000 to 30th June 2021. Studies examining unplanned readmissions of newborns within 31 days of discharge following the initial hospitalization at the time of their birth were included. Characteristics of the included studies examined variables and statistically significant risk factors were extracted from the inclusion studies. Extracted risk factors could not be pooled statistically due to the heterogeneity of the included studies. Data were synthesized using content analysis and presented in narrative and tabular form. Twenty-eight studies met the eligibility criteria, and 17 significant risk factors were extracted from the included studies. The most frequently cited risk factors associated with newborn readmissions were gestational age, postnatal length of stay, neonatal comorbidity, and feeding methods. The most frequently cited maternal-related risk factors which contributed to newborn readmissions were parity, race/ethnicity, and complications in pregnancy and/or perinatal period.

CONCLUSION

This systematic review identified a complex and diverse range of risk factors associated with 31-day UHR in newborn. Six of the 17 extracted risk factors were consistently cited by studies. Four factors were maternal (primiparous, mother being Asian, vaginal delivery, maternal complications), and two factors were neonatal (male infant and neonatal comorbidities). Implementation of evidence-based clinical practice guidelines for inpatient care and individualized hospital-to-home transition plans, including transition checklists and discharge readiness assessments, are recommended to reduce newborn UHRs.

WHAT IS KNOWN

• Attempts have been made to identify risk factors associated with newborn UHRs; however, the results are inconsistent.

WHAT IS NEW

• Six consistently cited risk factors related to newborn 31-day UHRs. Four maternal factors (primiparous, mother being Asian, vaginal delivery, maternal complications) and 2 neonatal factors (male infant and neonatal comorbidities). • The importance of discharge readiness assessment, including newborn clinical fitness for discharge and parental readiness for discharge. Future research is warranted to establish standardised maternal and newborn-related variables which healthcare providers can utilize to identify newborns at greater risk of UHRs and enable comparison of research findings.

Established and Novel Risk Factors for 30-Day Readmission Following Total Knee Arthroplasty: A Modified Delphi and Focus Group Study to Identify Clinically Important Predictors

Thirty-day readmission following total knee arthroplasty (TKA) is an important outcome influencing the quality of patient care and health system efficiency. The aims of this study were (1) to ascertain the clinical importance of established risk factors for 30-day readmission risk and give clinicians the opportunity to suggest and discuss novel risk factors and (2) to evaluate consensus on the importance of these risk factors. This study was conducted in two stages: a modified Delphi survey followed by a focus group. Orthopaedic surgeons and anaesthetists involved in the care of TKA patients completed an anonymous survey to judge the clinical importance of risk factors selected from a systematic review and meta-analysis and to suggest other clinically meaningful risk factors, which were then discussed in a focus group designed using elements of nominal group technique. Eleven risk factors received a majority (≥50%) vote of high importance in the Delphi survey overall, and six risk factors received a majority vote of high importance in the focus group overall. Lack of consensus highlighted the fact that this is a highly complex problem which is challenging to predict and which depends heavily on risk factors which may be open to interpretation, difficult to capture, and dependent upon personal clinical experience, which must be tailored to the individual patient.

A hybrid machine learning framework to improve prediction of all-cause rehospitalization among elderly patients in Hong Kong

BACKGROUND

Accurately estimating elderly patients' rehospitalisation risk benefits clinical decisions and service planning. However, research in rehospitalisation and repeated hospitalisation yielded only models with modest performance, and the model performance deteriorates rapidly as the prediction timeframe expands beyond 28 days and for older participants.

METHODS

A temporal zero-inflated Poisson (tZIP) regression model was developed and validated retrospectively and prospectively. The data of the electronic health records (EHRs) contain cohorts (aged 60+) in a major public hospital in Hong Kong. Two temporal offset functions accounted for the associations between exposure time and parameters corresponding to the zero-inflated logistic component and the Poisson distribution's expected count. tZIP was externally validated with a retrospective cohort's rehospitalisation events up to 12 months after the discharge date. Subsequently, tZIP was validated prospectively after piloting its implementation at the study hospital. Patients discharged within the pilot period were tagged, and the proposed model's prediction of their rehospitalisation was verified monthly. Using a hybrid machine learning (ML) approach, the tZIP-based risk estimator's marginal effect on 28-day rehospitalisation was further validated, competing with other factors representing different post-acute and clinical statuses.

RESULTS

The tZIP prediction of rehospitalisation from 28 days to 365 days was achieved at above 80% discrimination accuracy retrospectively and prospectively in two out-of-sample cohorts. With a large margin, it outperformed the Cox proportional and linear models built with the same predictors. The hybrid ML revealed that the risk estimator's contribution to 28-day rehospitalisation outweighed other features relevant to service utilisation and clinical status.

CONCLUSIONS

A novel rehospitalisation risk model was introduced, and its risk estimators, whose importance outweighed all other factors of diverse post-acute care and clinical conditions, were derived. The proposed approach relies on four easily accessible variables easily extracted from EHR. Thus, clinicians could visualise patients' rehospitalisation risk from 28 days to 365 days after discharge and screen high-risk older patients for follow-up care at the proper time.

Early prediction of 30- and 14-day all-cause unplanned readmissions

BACKGROUND

An unplanned readmission is a dual metric for both the cost and quality of medical care.

METHODS

We employed the random forest (RF) method to build a prediction model using a large dataset from patients' electronic health records (EHRs) from a medical center in Taiwan. The discrimination abilities between the RF and regression-based models were compared using the areas under the ROC curves (AUROC).

RESULTS

When compared with standardized risk prediction tools, the RF constructed using data readily available at admission had a marginally yet significantly better ability to identify high-risk readmissions within 30 and 14 days without compromising sensitivity and specificity. The most important predictor for 30-day readmissions was directly related to the representing factors of index hospitalization, whereas for 14-day readmissions the most important predictor was associated with a higher chronic illness burden.

CONCLUSIONS

Identifying dominant risk factors based on index admission and different readmission time intervals is crucial for healthcare planning.

Predicting Poor Outcomes Among Individuals Seeking Care for Major Depressive Disorder

Objective

To develop and validate algorithms to identify individuals with major depressive disorder (MDD) at elevated risk for suicidality or for an acute care event.

Methods

We conducted a retrospective cohort analysis among adults with MDD diagnosed between January 1, 2018 and February 28, 2019. Generalized estimating equation models were developed to predict emergency department (ED) visit, inpatient hospitalization, acute care visit (ED or inpatient), partial-day hospitalization, and suicidality in the year following diagnosis. Outcomes (per 1000 patients per month, PkPPM) were categorized as all-cause, psychiatric, or MDD-specific and combined into composite measures. Predictors included demographics, medical and pharmacy utilization, social determinants of health, and comorbid diagnoses as well as features indicative of clinically relevant changes in psychiatric health. Models were trained on data from 1.7M individuals, with sensitivity, positive predictive value, and area-under-the-curve (AUC) derived from a validation dataset of 0.7M.

Results

Event rates were 124.0 PkPPM (any outcome), 21.2 PkPPM (psychiatric utilization), and 7.6 PkPPM (suicidality). Among the composite models, the model predicting suicidality had the highest AUC (0.916) followed by any psychiatric acute care visit (0.891) and all-cause ED visit (0.790). Event-specific models all achieved an AUC >0.87, with the highest AUC noted for partial-day hospitalization (AUC = 0.938). Select predictors of all three outcomes included younger age, Medicaid insurance, past psychiatric ED visits, past suicidal ideation, and alcohol use disorder diagnoses, among others.

Conclusions

Analytical models derived from clinically-relevant features identify individuals with MDD at risk for poor outcomes and can be a practical tool for health care organizations to divert high-risk populations into comprehensive care models.

Development and Validation of a Machine Learning Model to Estimate Risk of Adverse Outcomes Within 30 Days of Opioid Dispensation

IMPORTANCE

Machine learning approaches can assist opioid stewardship by identifying high-risk opioid prescribing for potential interventions.

OBJECTIVE

To develop a machine learning model for deployment that can estimate the risk of adverse outcomes within 30 days of an opioid dispensation as a potential component of prescription drug monitoring programs using access to real-world data.

DESIGN, SETTING, AND PARTICIPANTS

This prognostic study used population-level administrative health data to construct a machine learning model. This study took place in Alberta, Canada (from January 1, 2018, to December 31, 2019), and included all patients 18 years and older who received at least 1 opioid dispensation from a community pharmacy within the province.

EXPOSURES

Each opioid dispensation served as the unit of analysis.

MAIN OUTCOMES AND MEASURES

Opioid-related adverse outcomes were identified from administrative data sets. An XGBoost model was developed on 2018 data to estimate the risk of hospitalization, an emergency department visit, or mortality within 30 days of an opioid dispensation; validation on 2019 data was done to evaluate model performance. Model discrimination, calibration, and other relevant metrics are reported using daily and weekly predictions on both ranked predictions and predicted probability thresholds using all data from 2019.

RESULTS

A total of 853 324 participants represented 6 181 025 opioid dispensations, with 145 016 outcome events reported (2.3%); 46.4% of the participants were men and 53.6% were women, with a mean (SD) age of 49.1 (15.6) years for men and 51.0 (18.0) years for women. Of the outcome events, 77 326 (2.6% pretest probability) occurred within 30 days of a dispensation in the validation set (XGBoost C statistic, 0.82 [95% CI, 0.81-0.82]). The top 0.1 percentile of estimated risk had a positive likelihood ratio (LR) of 28.7, which translated to a posttest probability of 43.1%. In our simulations, the weekly measured predictions had higher positive LRs in both the highest-risk dispensations and percentiles of estimated risk compared with predictions measured daily. Net benefit analysis showed that using machine learning prediction may not add additional benefit over the entire range of probability thresholds.

CONCLUSIONS AND RELEVANCE

These findings suggest that prescription drug monitoring programs can use machine learning classifiers to identify patients at risk of opioid-related adverse outcomes and intervene on high-risk ranked predictions. Better access to available administrative and clinical data could improve the prediction performance of machine learning classifiers and thus expand opioid stewardship efforts.

An AI-driven clinical care pathway to reduce 30-day readmission for chronic obstructive pulmonary disease (COPD) patients

Healthcare regulatory agencies have mandated a reduction in 30-day hospital readmission rates and have targeted COPD as a major contributor to 30-day readmissions. We aimed to develop and validate a simple tool deploying an artificial neural network (ANN) for early identification of COPD patients with high readmission risk. Using COPD patient data from eight hospitals within a large urban hospital system, four variables were identified, weighted and validated. These included the number of in-patient admissions in the previous 6 months, the number of medications administered on the first day, insurance status, and the Rothman Index on hospital day one. An ANN model was trained to provide a predictive algorithm and validated on an additional dataset from a separate time period. The model was implemented in a smartphone app (Re-Admit) incorporating four input risk factors, and a clinical care plan focused on high-risk readmission candidates was then implemented. Subsequent readmission data was analyzed to assess impact. The areas under the curve of receiver operating characteristics predicting readmission with ANN is 0.77, with sensitivity 0.75 and specificity 0.67 on the separate validation data. Readmission rates in the COPD high-risk subgroup after app and clinical intervention implementation saw a significant 48% decline. Our studies show the efficacy of ANN model on predicting readmission risks for COPD patients. The AI enabled Re-Admit smartphone app predicts readmission risk on day one of the patient's admission, allowing for early implementation of medical, hospital, and community resources to optimize and improve clinical care pathways.

Identification of elderly patients at risk for 30-day readmission: Clinical insight beyond big data prediction

AIM

This study explores the potential benefit of combining clinicians' risk assessments and the automated 30-day readmission prediction model.

BACKGROUND

Automated readmission prediction models based on electronic health records are increasingly applied as part of prevention efforts, but their accuracy is moderate.

METHODS

This prospective multisource study was based on self-reported surveys of clinicians and data from electronic health records. The survey was performed at 15 internal medicine wards of three general Clalit hospitals between May 2016 and June 2017. We examined the degree of concordance between the Preadmission Readmission Detection Model, clinicians' readmission risk classification and the likelihood of actual readmission. Decision trees were developed to classify patients by readmission risk.

RESULTS

A total of 694 surveys were collected for 371 patients. The disagreement between clinicians' risk assessment and the model was 34.5% for nurses and 33.5% for physicians. The decision tree algorithms identified 22% and 9% (based on nurses and physicians, respectively) of the model's low-medium-risk patients as high risk (accuracy 0.8 and 0.76, respectively).

CONCLUSIONS

Combining the Readmission Model with clinical insight improves the ability to identify high-risk elderly patients.

IMPLICATIONS FOR NURSING MANAGEMENT

This study provides algorithms for the decision-making process for selecting high-risk readmission patients based on nurses' evaluations.

Identifying patients at risk of unplanned re-hospitalisation using statewide electronic health records

Preventing unplanned hospitalisations, including readmissions and re-presentations to the emergency department, is an important strategy for addressing the growing demand for hospital care. Significant successes have been reported from interventions put in place by hospitals to reduce their incidence. However, there is limited use of data-driven algorithms in hospital services to identify patients for enrolment into these intervention programs. Here we present the results of a study aiming to develop algorithms deployable at scale as part of a state government’s initiative to address rehospitalizations and which fills several gaps identified in the state-of-the-art literature. To the best of our knowledge, our study involves the largest-ever sample size for developing risk models. Logistic regression, random forests and gradient boosted techniques were explored as model candidates and validated retrospectively on five years of data from 27 hospitals in Queensland, Australia. The models used a range of predictor variables sourced from state-wide Emergency Department(ED), inpatient, hospital-dispensed medications and hospital-requested pathology databases. The investigation leads to several findings: (i) the advantage of looking at a longer patient data history, (ii) ED and inpatient datasets alone can provide useful information for predicting hospitalisation risk and the addition of medications and pathology test results leads to trivial performance improvements, (iii) predicting readmissions to the hospital was slightly easier than predicting re-presentations to ED after an inpatient stay, which was slightly easier again than predicting re-presentations to ED after an EDstay, (iv) a gradient boosted approach (XGBoost) was systematically the most powerful modelling approach across various tests.

Depressive symptoms and malnutrition are associated with other geriatric syndromes and increase risk for 30-Day readmission in hospitalized older adults: a prospective cohort study

BACKGROUND

Readmission in older adults is typically complex with multiple contributing factors. We aim to examine how two prevalent and potentially modifiable geriatric conditions - depressive symptoms and malnutrition - relate to other geriatric syndromes and 30-day readmission in hospitalized older adults.

METHODS

Consecutive admissions of patients ≥ 65 years to a general medical department were recruited over 16 months. Patients were screened for depression, malnutrition, delirium, cognitive impairment, and frailty at admission. Medical records were reviewed for poor oral intake and functional decline during hospitalization. Unplanned readmission within 30-days of discharge was tracked through the hospital's electronic health records and follow-up telephone interviews. We use directed acyclic graphs (DAGs) to depict the relationship of depressive symptoms and malnutrition with geriatric syndromes that constitute covariates of interest and 30-day readmission outcome. Multiple logistic regression was performed for the independent associations of depressive symptoms and malnutrition with 30-day readmission, adjusting for variables based on DAG-identified minimal adjustment set.

RESULTS

We recruited 1619 consecutive admissions, with mean age 76.4 (7.9) years and 51.3% females. 30-day readmission occurred in 331 (22.0%) of 1,507 patients with follow-up data. Depressive symptoms, malnutrition, higher comorbidity burden, hospitalization in the one-year preceding index admission, frailty, delirium, as well as functional decline and poor oral intake during the index admission, were more commonly observed among patients who were readmitted within 30 days of discharge (P < 0.05). Patients with active depressive symptoms were significantly more likely to be frail (OR = 1.62, 95% CI 1.22-2.16), had poor oral intake (OR = 1.35, 95% CI 1.02-1.79) and functional decline during admission (OR = 1.58, 95% CI 1.11-2.23). Malnutrition at admission was significantly associated with frailty (OR = 1.53, 95% CI 1.07-2.19), delirium (OR = 2.33, 95% CI 1.60-3.39) cognitive impairment (OR = 1.88, 95% CI 1.39-2.54) and poor oral intake during hospitalization (OR = 2.70, 95% CI 2.01-3.64). In minimal adjustment set identified by DAG, depressive symptoms (OR = 1.38, 95% CI 1.02-1.86) remained significantly associated with 30-day readmission. The association of malnutrition with 30-day readmission was no longer statistically significant after adjusting for age, ethnicity and depressive symptoms in the minimal adjustment set (OR = 1.40, 95% CI 0.99-1.98).

CONCLUSION

The observed causal associations support screening and targeted interventions for depressive symptoms and malnutrition during admission and in the post-acute period.

Reliability, Validity, and Responsiveness of the DEG, a Three-Item Dyspnea Measure

BACKGROUND

Dyspnea is a common and debilitating symptom that affects many different patient populations. Dyspnea measures should assess multiple domains.

OBJECTIVE

To evaluate the reliability, validity, and responsiveness of an ultra-brief, multi-dimensional dyspnea measure.

DESIGN

We adapted the DEG from the PEG, a valid 3-item pain measure, to assess average dyspnea intensity (D), interference with enjoyment of life (E), and dyspnea burden with general activity (G).

PARTICIPANTS

We used data from a multi-site randomized clinical trial among outpatients with heart failure.

MAIN MEASURES

We evaluated reliability (Cronbach's alpha), concurrent validity with the Memorial-Symptom-Assessment-Scale (MSAS) shortness-of-breath distress-orbothersome item and 7-item Generalized-Anxiety-Disorder (GAD-7) scale, knowngroups validity with New-York-Heart-Association-Functional-Classification (NYHA) 1-2 or 3-4 and presence or absence of comorbid chronic obstructive pulmonary disease (COPD), responsiveness with the MSAS item as an anchor, and calculated a minimal clinically important difference (MCID) using distribution methods.

KEY RESULTS

Among 312 participants, the DEG was reliable (Cronbach's alpha 0.92). The mean (standard deviation) DEG score was 5.26 (2.36) (range 0-10) points. DEG scores correlated strongly with the MSAS shortness of breath distress-or-bothersome item (r=0.66) and moderately with GAD-7 categories (ρ=0.36). DEG scores were statistically significantly lower among patients with NYHA 1-2 compared to 3-4 [mean difference (standard error): 1.22 (0.27) points, p<0.01], and those without compared to with comorbid COPD [0.87 (0.27) points, p<0.01]. The DEG was highly sensitive to change, with MCID of 0.59-1.34 points, or 11-25% change.

CONCLUSIONS

The novel, ultra-brief DEG measure is reliable, valid, and highly responsive. Future studies should evaluate the DEG's sensitivity to interventions, use anchor-based methods to triangulate MCID estimates, and determine its prognostic usefulness among patients with chronic cardiopulmonary and other diseases.

Decision support through risk cost estimation in 30-day hospital unplanned readmission

Unplanned hospital readmissions mean a significant burden for health systems. Accurately estimating the patient's readmission risk could help to optimise the discharge decision-making process by smartly ordering patients based on a severity score, thus helping to improve the usage of clinical resources. A great number of heterogeneous factors can influence the readmission risk, which makes it highly difficult to be estimated by a human agent. However, this score could be achieved with the help of AI models, acting as aiding tools for decision support systems. In this paper, we propose a machine learning classification and risk stratification approach to assess the readmission problem and provide a decision support system based on estimated patient risk scores.

A bias evaluation checklist for predictive models and its pilot application for 30-day hospital readmission models

OBJECTIVE

Health care providers increasingly rely upon predictive algorithms when making important treatment decisions, however, evidence indicates that these tools can lead to inequitable outcomes across racial and socio-economic groups. In this study, we introduce a bias evaluation checklist that allows model developers and health care providers a means to systematically appraise a model's potential to introduce bias.

MATERIALS AND METHODS

Our methods include developing a bias evaluation checklist, a scoping literature review to identify 30-day hospital readmission prediction models, and assessing the selected models using the checklist.

RESULTS

We selected 4 models for evaluation: LACE, HOSPITAL, Johns Hopkins ACG, and HATRIX. Our assessment identified critical ways in which these algorithms can perpetuate health care inequalities. We found that LACE and HOSPITAL have the greatest potential for introducing bias, Johns Hopkins ACG has the most areas of uncertainty, and HATRIX has the fewest causes for concern.

DISCUSSION

Our approach gives model developers and health care providers a practical and systematic method for evaluating bias in predictive models. Traditional bias identification methods do not elucidate sources of bias and are thus insufficient for mitigation efforts. With our checklist, bias can be addressed and eliminated before a model is fully developed or deployed.

CONCLUSION

The potential for algorithms to perpetuate biased outcomes is not isolated to readmission prediction models; rather, we believe our results have implications for predictive models across health care. We offer a systematic method for evaluating potential bias with sufficient flexibility to be utilized across models and applications.

Re-admission following discharge from a Geriatric Evaluation and Management Unit: identification of risk factors

ObjectiveTo establish independent factors that influence the likelihood of re-admission within 30 days of discharge from a Geriatric Evaluation and Management Unit.MethodsAn observational prospective cohort design using clinical data extracted from the medical charts of eligible patients discharged from a tertiary public hospital Geriatric Evaluation and Management Unit between July 2017 and April 2019. Binary logistic regression was undertaken to determine variables that increased the likelihood of hospital re-admission (dependent variable).ResultsA total of 367 patients were eligible for inclusion, with 69 patients re-admitted within 30 days of discharge. Univariate analysis demonstrated significant differences between groups (re-admission vs non-re-admission) with respect to Charlson Comorbidity Index (CCI) (7.4 [2.4] vs 6.3 [2.2], P = 0.001), Clinical Frailty Scale (CFS) (5.6 [1.1] vs 5.2 [1.34], P = 0.02), and documented malnourishment (36.2% vs 23.6%, P = 0.04). All three variables remained significant when entered into the regression model (X2 = 25.095, P < 0.001). A higher score for the CFS (OR 1.3; 95% CI 1.03-1.64; P = 0.03) and CCI (OR 1.2; 95% CI 1.06-1.33; P = 0.004), and documented malnourishment (OR 1.92; 95% CI 1.06-3.47; P = 0.03) were all independent factors that increased the likelihood of patient re-admission within 30 days of discharge.ConclusionsThis study supports the formal inclusion of the CCI and CFS into routine practice in Geriatric Evaluation and Management Units. The inclusion of the measures can help inform future discharge planning practices. Clinicians should use malnourishment status, CCI and CFS to identify at risk patients and target discharge planning interventions accordingly.

Clinical characteristics and social determinants of health associated with 30-day hospital readmissions of patients with COVID-19

COVID-19 readmissions are associated with increased patient mortality and healthcare system strain. This retrospective cohort study of PCR-confirmed COVID-19 positive adults (>18 years) hospitalized and readmitted within 30 days of discharge from index admission was performed at eight Atlanta hospitals from March to December 2020. The objective was to describe COVID-19 patient-level demographics and clinical characteristics, and community-level social determinants of health (SDoH) that contribute to 30-day readmissions. Demographics, comorbidities, COVID-19 treatment, and discharge disposition data were extracted from the index admission. ZIP codes were linked to a demographic/lifestyle database interpolating to community-level SDoH. Of 7155 patients with COVID-19, 463 (6.5%) had 30-day, unplanned, all-cause hospital readmissions. Statistically significant differences were not found in readmissions stratified by age, sex, race, or ethnicity. Patients with a high-risk Charlson Comorbidity Index had higher odds of readmission (OR 4.8 (95% CI: 2.1 to 11.0)). Remdesivir treatment and intensive care unit (ICU) care were associated with lower odds of readmission (OR 0.5 (95% CI: 0.4 to 0.8) and OR 0.5 (95% CI: 0.4 to 0.7), respectively). Patients residing in communities with larger average household size were less likely to be readmitted (OR 0.7 (95% CI: 0.5 to 0.9). In this cohort, patients who received remdesivir, were cared for in an ICU, and resided in ZIP codes with higher proportions of residents with increased social support had lower odds of readmission. These patient-level factors and community-level SDoH may be used to identify patients with COVID-19 who are at increased risk of readmission.

Comparison of Mortality and Hospital Readmissions Among Patients Receiving Virtual Ward Transitional Care vs Usual Postdischarge Care: A Systematic Review and Meta-analysis

IMPORTANCE

Virtual wards (VWs) include patient assessment in their homes by health care personnel and offer ongoing assessment and case management via home, telephone, and/or clinic visits. The association between VWs and patient outcomes during the transition from the hospital to home are unclear; earlier reviews on this topic have often conflated telemonitoring programs with VW models.

OBJECTIVE

To evaluate the use of VW transition systems for community-dwelling individuals after medical discharge.

DATA SOURCES

English-language articles indexed in PubMed or Cochrane and published between January 1, 2000, and June 15, 2021.

STUDY SELECTION

Randomized clinical trials comparing VW care with usual postdischarge care. Studies were stratified by diagnosis.

DATA EXTRACTION AND SYNTHESIS

Following the Preferred Reporting Items for Systematic Reviews and Meta-analyses guideline, 2 reviewers independently identified studies and extracted data. DerSimonian-Laird inverse variance weighted random-effects models were used to compute relative risks (RRs) for dichotomous outcomes and mean differences for continuous outcomes.

MAIN OUTCOMES AND MEASURES

All-cause mortality, hospital readmissions, emergency department visits, health care costs, readmission length of stay, quality of life, and functional status.

RESULTS

Twenty-four randomized clinical trials (11 in patients with heart failure, 3 in patients with chronic obstructive pulmonary disease, 4 in patients at high-risk for readmission, and 6 in mixed patient populations) with 10 876 patients were included (20 more trials than earlier reviews). In patients with heart failure, VWs were associated with fewer deaths (RR, 0.86; 95% CI, 0.76-0.97) and fewer readmissions (RR, 0.84; 95% CI, 0.74-0.96). However, similar associations were not seen in randomized clinical trials enrolling patients with other diagnoses (RR, 0.93; 95% CI, 0.83-1.04 for mortality and RR, 0.96; 95% CI, 0.88-1.05 for readmissions). Across all studies, VWs were associated with fewer emergency department visits (RR, 0.83; 95% CI, 0.70-0.98) and shorter readmission lengths of stay (mean difference, -1.94 days; 95% CI, -3.28 to -0.60 days). Three of 7 studies that evaluated health care expenses reported statistically significant lower costs with VW transition systems.

CONCLUSIONS AND RELEVANCE

Although postdischarge VW interventions appear to be associated with fewer subsequent emergency department visits, shorter readmission lengths of stay, and lower health care costs, fewer deaths and readmissions were seen only in trials enrolling patients with heart failure.

Forecasting Hospital Readmissions with Machine Learning

Hospital readmissions are regarded as a compounding economic factor for healthcare systems. In fact, the readmission rate is used in many countries as an indicator of the quality of services provided by a health institution. The ability to forecast patients’ readmissions allows for timely intervention and better post-discharge strategies, preventing future life-threatening events, and reducing medical costs to either the patient or the healthcare system. In this paper, four machine learning models are used to forecast readmissions: support vector machines with a linear kernel, support vector machines with an RBF kernel, balanced random forests, and weighted random forests. The dataset consists of 11,172 actual records of hospitalizations obtained from the General Hospital of Komotini “Sismanogleio” with a total of 24 independent variables. Each record is composed of administrative, medical-clinical, and operational variables. The experimental results indicate that the balanced random forest model outperforms the competition, reaching a sensitivity of 0.70 and an AUC value of 0.78.

Evaluation of the association of length of stay in hospital and outcomes

BACKGROUND

There exist wide variations in healthcare quality within the National Health Service (NHS). A shorter hospital length of stay (LOS) has been implicated as premature discharge, that may in turn lead to adverse consequences. We tested the hypothesis that a short LOS might be associated with increased risk of readmissions within 28 days of hospital discharge and also post-discharge mortality.

METHODS

We conducted a single-centred study of 32 270 (46.1% men) consecutive alive-discharge episodes (mean age = 64.0 years, standard deviation = 20.5, range = 18-107 years), collected between 01/04/2017 and 31/03/2019. Associations of LOS tertiles (middle tertile as a reference) with readmissions and mortality were assessed using observed/expected ratios, and logistic and Cox regressions to estimate odds (OR) and hazard ratios (HR) (adjusted for age, sex, patients' severity of underlying health status and index admissions), with 95% confidence intervals (CIs).

RESULTS

The observed numbers of readmissions within 28 days of hospital discharge or post-discharge mortality were lower than expected (observed: expected ratio < 1) in patients in the bottom tertile (<1.2 days) and middle tertile (1.2-4.3 days) of LOS, whilst higher than expected (observed: expected ratio > 1) in patients in the top tertile (>4.3 days), amongst all ages. Patients in the top tertile of LOS had increased risks for one readmission: OR = 2.32 (95% CI = 1.86-2.88) or ≥2 readmissions: OR = 6.17 (95% CI = 5.11-7.45), death within 30 days: OR = 2.87 (95% CI = 2.34-3.51), and within six months of discharge: OR = 2.52 (95% CI = 2.23-2.85), and death over a two-year period: HR = 2.25 (95% CI = 2.05-2.47). The LOS explained 7.4% and 15.9% of the total variance (r2) in one readmission and ≥2 readmissions, and 9.1% and 10.0% of the total variance in mortality with 30 days and within six months of hospital discharge, respectively. Within the bottom, middle and top tertiles of the initial LOS, the median duration from hospital discharge to death progressively shortened from 136, 126 to 80 days, whilst LOS during readmission lengthened from 0.4, 0.9 to 2.8 days, respectively.

CONCLUSION

Short LOS in hospital was associated with favourable post-discharge outcomes such as early readmission and mortality, and with a delay in time interval from discharge to death and shorter LOS in hospital during readmission. These findings indicate that timely discharge from our hospital meets the aims of the NHS-generated national improvement programme, Getting It Right First Time.

Applicability of predictive models for 30-day unplanned hospital readmission risk in paediatrics: a systematic review

OBJECTIVES

To summarise multivariable predictive models for 30-day unplanned hospital readmissions (UHRs) in paediatrics, describe their performance and completeness in reporting, and determine their potential for application in practice.

DESIGN

Systematic review.

DATA SOURCE

CINAHL, Embase and PubMed up to 7 October 2021.

ELIGIBILITY CRITERIA

English or German language studies aiming to develop or validate a multivariable predictive model for 30-day paediatric UHRs related to all-cause, surgical conditions or general medical conditions were included.

DATA EXTRACTION AND SYNTHESIS

Study characteristics, risk factors significant for predicting readmissions and information about performance measures (eg, c-statistic) were extracted. Reporting quality was addressed by the 'Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis' (TRIPOD) adherence form. The study quality was assessed by applying six domains of potential biases. Due to expected heterogeneity among the studies, the data were qualitatively synthesised.

RESULTS

Based on 28 studies, 37 predictive models were identified, which could potentially be used for determining individual 30-day UHR risk in paediatrics. The number of study participants ranged from 190 children to 1.4 million encounters. The two most common significant risk factors were comorbidity and (postoperative) length of stay. 23 models showed a c-statistic above 0.7 and are primarily applicable at discharge. The median TRIPOD adherence of the models was 59% (P₂₅-P₇₅, 55%-69%), ranging from a minimum of 33% to a maximum of 81%. Overall, the quality of many studies was moderate to low in all six domains.

CONCLUSION

Predictive models may be useful in identifying paediatric patients at increased risk of readmission. To support the application of predictive models, more attention should be placed on completeness in reporting, particularly for those items that may be relevant for implementation in practice.

Human Factors Considerations in Transitions in Care Clinical Decision Support System Implementation Studies

Objective: Review transitions in care clinical decision support system (CDSS) implementation studies and describe human factors considerations in users, design, alert types, intervention timing, and implementation outcomes. Methods: Literature review in PubMed guided by subject matter experts. Results: Twelve articles were included. Targeted users included physicians, nurses, pharmacists, or interdisciplinary teams. Alerts were deployed via email, cloud-based software, or the EHR in inpatient and/or outpatient settings. Outcome measures varied across articles, with mixed performance. There were six readmissions-focused, two prescribing, one laboratory, two prescribing and laboratory, and one discharge disposition CDSS. Few articles reported statistically significant differences in outcomes, and many reported alert fatigue. Discussion and Conclusion: Despite the increasing prevalence of CDSS for transitions in care, few articles describe implementation processes and outcomes, and evidence of clinical practice improvement is mixed. Future studies should utilize implementation science frameworks and incorporate appropriate implementation outcomes in addition to traditional clinical outcomes like readmission rates.

Intervention by a clinical pharmacist carried out at discharge of elderly patients admitted to the internal medicine department: influence on readmissions and costs

BACKGROUND

Patient education on pharmacological treatment could reduce readmissions. Our objective was to carry out a pharmacist intervention focused on providing information about high-risk medications to chronic patients and to analyse its influence on readmissions and costs.

METHODS

A single-centre study with an intervention group and a retrospective control group was conducted. The intervention was carried out in all polymedicated patients ≥ 65 years who were admitted to internal medicine and signed the informed consent between June 2017 and February 2018. Patients discharged to nursing homes or long-term hospitals were excluded. The control group were all the patients who were admitted during the same months of 2014 who met the same inclusion criteria. The patients were classified according to the HOSPITAL score as having a low, intermediate, or high risk of potentially avoidable readmission. Outcome measures were 30-day readmission and cost data. To analyse the effect of the intervention on readmission, a logistic regression was performed.

RESULTS

The study included 589 patients (286 intervention group; 303 control group). The readmission rate decreased from 20.13% to 16.43% in the intervention group [OR = 0.760 95% CI (0.495-1.166); p = 0.209)]. The incremental cost for the intervention to prevent one readmission was €3,091.19, and the net cost saving was €1,301.26. In the intermediate- and high-risk groups, readmissions were reduced 10.91% and 10.00%, and the net cost savings were €3,3143.15 and €3,248.71, respectively.

CONCLUSIONS

The pharmacist intervention achieved savings in the number of readmissions, and the net cost savings were greater in patients with intermediate and high risks of potentially avoidable readmission according to the HOSPITAL score.

Machine learning for predicting readmission risk among the frail: Explainable AI for healthcare

Healthcare costs due to unplanned readmissions are high and negatively affect health and wellness of patients. Hospital readmission is an undesirable outcome for elderly patients. Here, we present readmission risk prediction using five machine learning approaches for predicting 30-day unplanned readmission for elderly patients (age ≥ 50 years). We use a comprehensive and curated set of variables that include frailty, comorbidities, high-risk medications, demographics, hospital, and insurance utilization to build these models. We conduct a large-scale study with electronic health record (her) data with over 145,000 observations from 76,000 patients. Findings indicate that the category boost (CatBoost) model outperforms other models with a mean area under the curve (AUC) of 0.79. We find that prior readmissions, discharge to a rehabilitation facility, length of stay, comorbidities, and frailty indicators were all strong predictors of 30-day readmission. We present in-depth insights using Shapley additive explanations (SHAP), the state of the art in machine learning explainability.

A review of literature on risk prediction tools for hospital readmissions in older adults

PURPOSE

The purpose of this paper is to identify and analyse the readmission risk prediction tools reported in the literature and their benefits when it comes to healthcare organisations and management.

DESIGN/METHODOLOGY/APPROACH

Readmission risk prediction is a growing topic of interest with the aim of identifying patients in particular those suffering from chronic diseases such as congestive heart failure, chronic obstructive pulmonary disease and diabetes, who are at risk of readmission. Several models have been developed with different levels of predictive ability. A structured and extensive literature search of several databases was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-analysis strategy, and this yielded a total of 48,984 records.

FINDINGS

Forty-three articles were selected for full-text and extensive review after following the screening process and according to the eligibility criteria. About 34 unique readmission risk prediction models were identified, in which their predictive ability ranged from poor to good (c statistic 0.5-0.86). Readmission rates ranged between 3.1 and 74.1% depending on the risk category. This review shows that readmission risk prediction is a complex process and is still relatively new as a concept and poorly understood. It confirms that readmission prediction models hold significant accuracy at identifying patients at higher risk for such an event within specific context.

RESEARCH LIMITATIONS/IMPLICATIONS

Since most prediction models were developed for specific populations, conditions or hospital settings, the generalisability and transferability of the predictions across wider or other contexts may be difficult to achieve. Therefore, the value of prediction models remains limited to hospital management. Future research is indicated in this regard.

ORIGINALITY/VALUE

This review is the first to cover readmission risk prediction tools that have been published in the literature since 2011, thereby providing an assessment of the relevance of this crucial KPI to health organisations and managers.

The predictive utility of functional status at discharge: a population-level cohort analysis

Background

Functional status is a patient-important, patient-centered measurement. The utility of functional status measures to inform post-discharge patient needs is unknown. We sought to examine the utility of routinely collected functional status measures gathered from older hospitalized patients to predict a panel of post-discharge outcomes.

Methods

In this population-based retrospective cohort study, Adults 65+ discharged from an acute hospitalization between 4 November 2008 and 18 March 2016 in Ontario, Canada and received an assessment of functional status at discharge using the Health Outcomes for Better Information and Care tool were included. Multivariable regression analysis was used to determine the relationship between functional status and emergency department (ED) re-presentation, hospital readmission, long term care facility (LTCF) admission or wait listing (‘LTCF readiness’), and death at 180 days from discharge.

Results

A total of 80 020 discharges were included. 38 928 (48.6%) re-presented to the ED, 24 222 (30.3%) were re-admitted, 5 037 (6.3%) were LTCF ready, and 9 047 (11.3%) died at 180 days. Beyond age, diminished functional status at discharge was the factor most associated with LTCF readiness (adjusted Odds Ratio [OR] 4.11 for those who are completely dependent for activities of daily living compared to those who are independent; 95% Confidence Interval [CI]: 3.70-4.57) and death (OR 3.99; 95% CI: 3.67-4.35). Functional status also had a graded relationship with each outcome and improved the discriminability of the models predicting death and LTCF readiness (p<0.01) but not ED re-presentation or hospital re-admission.

Conclusion

Routinely collected functional status at discharge meaningfully improves the prediction of long term care home readiness and death. The routine assessment of functional status can inform post-discharge care and planning for older adults.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12877-021-02652-6.